Research Archives - HPC Montenegro

27.07.2026.27.07.2026.

BSc Thesis: BabyFlow.AI – A Mobile Assistant for Early Parenthood Support

Marija Gardašević successfully defended her BSc thesis, “Application of Artificial Intelligence in the Development of a Mobile Assistant for Early Parenthood Support,” at the Faculty for Information Systems and Technologies, University of Donja Gorica. Supervised by Prof. Tomo Popović, the thesis resulted in BabyFlow.AI, a functional Flutter-based mobile prototype for recording and reviewing a baby’s daily routines, including sleep, feeding, mood, meals and basic health-related information. The prototype may be considered an early proof of concept for a future digital parenting-support product, subject to further user testing, integration of more advanced analytics and validation in cooperation with relevant professionals.

ABSTRACT – The thesis presents the development of BabyFlow.AI, a functional mobile application prototype designed to help parents organize and monitor a baby’s daily routine. The application combines modules for sleep, feeding, pumping, mood, meals, calming-noise sessions, vaccination records, growth tracking and relevant health-information resources, while storing user data locally on the device. Basic analytical insights are generated from user entries, and a separate demonstrative Python machine-learning model illustrates a simple data-processing and classification workflow. BabyFlow.AI is not intended for medical, clinical or diagnostic use, but represents a practical proof of concept that could support the future development of privacy-conscious digital services for parents and childcare providers.

27.07.2026.27.07.2026.

BSc Thesis: AI and HPC for Cybersecurity of Connected Vehicles

Anđela Vuković successfully defended her BSc thesis, “Application of AI and HPC Technologies in the Cybersecurity of Connected Vehicles,” at the Faculty for Information Systems and Technologies, University of Donja Gorica. Supervised by Prof. Tomo Popović, with the support of Arnad Lekić, the thesis combines an analysis of automotive cybersecurity with a practical AI model for detecting anomalies in CAN communication. The developed demonstrator can be regarded as an early proof of concept for potential industrial applications, subject to further testing with real vehicle data and deployment-oriented validation.

ABSTRACT – This thesis examines the application of Artificial Intelligence (AI) and High-Performance Computing (HPC) in the cybersecurity of connected vehicles. In addition to analysing contemporary cybersecurity risks, communication technologies and protection mechanisms, the thesis presents a practical implementation of an autoencoder model for detecting anomalous CAN messages. The experimental model demonstrated the potential of AI-based anomaly detection, while HPC is considered an important enabler for processing larger datasets, training more advanced models and simulating cyberattack scenarios. Although developed using simulated data, the implementation provides an initial proof of concept that could be extended and validated for use by automotive manufacturers, cybersecurity providers, testing laboratories and fleet operators.

30.06.2026.10.07.2026.

MSc Thesis Defence: Quantization of Edge AI Models in IoT Systems

On June 29, 2026, an MSc thesis entitled “Quantization of Edge AI Models in IoT Systems” by Mr. Zarko Perunicic was successfully defended within the Artificial Intelligence Master’s programme at the University of Donja Gorica. Through its participation in the programme, mentoring activities, and support for practical research in AI, HPC, and IoT, NCC Montenegro contributes to developing advanced competencies in the efficient deployment of artificial intelligence models on resource-constrained devices. The thesis addresses an important Edge AI challenge by evaluating model quantization strategies for computer vision applications in IoT environments.

ABSTRACT – Edge AI systems in Internet of Things (IoT) environments require artificial intelligence models that are sufficiently small, fast, and reliable to operate on resource-constrained devices. This thesis examines how quantization, as a model optimization method, affects the performance of a computer vision model in the task of grape leaf disease classification. MobileNetV2 was used as the reference model, and its optimized variants were then prepared in the TensorFlow Lite environment using FP16 and INT8 quantization modes, including dynamic INT8 quantization, full INT8 quantization based on a representative dataset, and an INT8 variant obtained through quantization-aware training (QAT) on an additional, more challenging dataset. The experiments were conducted on cleaned and restructured subsets, following quality control of publicly available datasets and the removal of redundant and visually equivalent samples. Under controlled conditions, latency, execution stability, peak RAM usage, model size, and accuracy were analyzed.

On the more controlled dataset, full post-training INT8 quantization achieved the most favorable balance among efficiency, stability, and model size while preserving accuracy, whereas dynamic INT8 quantization, despite reducing model size, can measurably slow down model execution. On the more challenging field dataset, this pattern changed partially: although full INT8 quantization remained the fastest variant, the INT8 model obtained through QAT provided the most favorable overall balance between accuracy, model size, and latency. The results show that the effect of quantization depends not only on numerical precision, but also on data characteristics, the calibration procedure, and the compatibility of the model with the execution environment. It is therefore concluded that the choice of quantization strategy should be empirically validated for a specific application scenario rather than assumed in advance.

29.06.2026.10.07.2026.

MSc Thesis Defence: Synergy of Computer Vision and Natural Language Processing in Tuberculosis Diagnostics and Education

On June 29, 2026, MSc candidate Nikola Kavarić successfully defended his thesis entitled “Synergy of Computer Vision and Natural Language Processing in Tuberculosis Diagnostics and Education” within the Artificial Intelligence Master’s programme at the University of Donja Gorica. Through its support for the programme, mentoring activities, and development of competencies in artificial intelligence and high-performance computing, NCC Montenegro contributes to preparing young researchers to develop interdisciplinary AI solutions for healthcare. The thesis investigates the combination of computer vision and Retrieval-Augmented Generation approaches for detecting signs of tuberculosis and providing educational explanations of medical findings.

ABSTRACT – The aim of this thesis is the development and evaluation of a system that combines computer vision and Retrieval-Augmented Generation (RAG) models for the automatic detection of signs of tuberculosis in chest X-ray images and the educational explanation of findings. The initial hypothesis was that it is possible to develop a functional prototype capable of recognizing pathological changes in X-ray images and generating informative, literature-grounded responses for users. Within this research, a CNN model for binary classification and YOLO models for the localization of pathological changes were developed and evaluated. The CNN model achieved an accuracy of 97% on the test set, representing a solid and measurable contribution. The YOLO models adequately demonstrated the concept of localization, with certain limitations related to dataset size and class imbalance. In addition to the visual module, a RAG prototype was implemented, utilizing a local medical document base to generate responses to user queries. The integration was implemented at the prototype level, without clinical validation. Based on the obtained results, the hypothesis was partially confirmed — to a significant extent for the CNN classification component within the test dataset used, while the YOLO and RAG components, due to dataset limitations and the absence of expert-verified reference answers, should be treated as proof-of-concept components. The thesis demonstrates that a modular combination of these technologies can serve as a useful foundation for the development of educational tools in the field of medical diagnostics.

29.06.2026.10.07.2026.

MSc Thesis Defence: Machine Learning and AI Model Development for Medical Applications

On June 29, 2026, MSc candidate Anesa Abazović successfully defended her thesis entitled “Machine Learning and AI Model Development for Medical Applications” within the Artificial Intelligence Master’s programme at the University of Donja Gorica. Through its support for the programme, mentoring activities, and development of competencies in artificial intelligence and high-performance computing, NCC Montenegro contributes to preparing young researchers to apply advanced AI methods in medicine and other socially relevant domains. The thesis investigates the application of machine learning and deep learning to medical image analysis and clinical data classification, while also considering the technical, ethical, and practical challenges of integrating AI systems into healthcare.

ABSTRACT – This thesis explores the potential of machine learning (ML) and deep learning (DL) models in the detection of ovarian cancer and the prediction of pneumonia. In the first part, a YOLO model was used to identify tumor lesions in medical images, while in the second part, XGBoost, Random Forest, and neural network models were applied for the classification of clinical data. Model performance was evaluated using metrics such as precision, recall, accuracy, specificity, F1-score, ROC-AUC, MCC, mAP50, and mAP50-95. The experimental analysis demonstrated that AI models can achieve promising performance in both clinical scenarios, with certain limitations that require further validation. In addition to technical aspects, ethical considerations were also examined, including model interpretability, data privacy, and the integration of AI systems into healthcare information systems. It is concluded that AI can provide significant support to modern diagnostics, with the need for further improvements and clinical validation.

08.04.2026.11.05.2026.

HPC Use Case: Large-Scale Text Analysis of Industrial Policy

Within the EuroCC initiative, this project demonstrates how High Performance Computing (HPC) enables a new approach to analysing industrial policy through large-scale text data.

Modern innovation policies are increasingly embedded in strategies, reports, and policy documents. This project treats those documents as data, transforming them into measurable indicators that can be linked to national innovation performance.

From Raw Data to Analytical Insights -The study started with over 50,000 policy documents and processed more than 36,000 clean texts, resulting in a structured dataset of 825 country-year observations across 55 countries (2007–2021).

Using Natural Language Processing (NLP), the project extracts key policy signals, including:

policy attention (how much a topic is discussed)
policy orientation (whether it is framed positively or negatively)

These signals allow policy discourse to be analyzed quantitatively and linked to innovation outcomes.

HPC infrastructure was essential for executing the full pipeline.

The complete workflow was finished in approximately 16 hours, while the same process on a standard laptop would take several weeks.

This enabled large-scale data processing, rapid iteration of models, and robust cross-country analysis.

The results show that industrial policy does not have a uniform effect on innovation. Instead, its impact depends on both the type of policy and how it is communicated.

Key insights include:

different policy categories influence innovation outcomes differently
scientific publications respond faster than patents or R&D investment
text-based policy signals can serve as early indicators of changes in innovation environments

Impact – This project highlights how HPC enables:

transformation of unstructured text into analytical datasets
integration of policy analysis with economic outcomes
development of new tools for monitoring innovation systems

It also demonstrates the value of policy documents as a strategic data source for researchers, firms, and policymakers.

03.03.2026.18.03.2026.

Conference paper at IEEE IT2026 on intepretable ML for diabetes screening

AI-AGE team presented a paper titled “Interpretable ML for Diabetes and Prediabetes Screening Using Self-Reported Health Indicators” by S. Lazic, S. Cakic, I. Rubezic Lukic, N. Popovic, and T. Popovic at the 30. Annual Conferenc on Information Technology IT 2026. This was part of mentoring activities and efforts related to development of young researchers.

ABSTRACT – Early identification of type 2 diabetes (T2D) and prediabetes enables timely interventions, yet screening often relies on self-reported data rather than laboratory testing. This work compares lightweight Machine Learning (ML) models: Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Multilayer Perceptron (MLP) trained on 21 self-reported indicators from the 2015 Behavioral Risk Factor Surveillance System (BRFSS) dataset for three-class classification (no diabetes, prediabetes, diabetes). We propose a screening-oriented evaluation where a probability threshold is selected to achieve a target sensitivity (recall) of 0.80. LightGBM achieves balanced accuracy of 0.52 and precision of 0.33 at the target sensitivity, with 38% of cases flagged. Tree SHapley Additive exPlanations (TreeSHAP) highlight general health status, age category, body mass index (BMI), and hypertension as dominant predictors. A FastAPI web application provides individual risk estimates and instance-level explanations. The pipeline demonstrates feasibility of interpretable, calibrated screening from non-laboratory data.